{"id":"W3113785905","doi":"10.48550/arxiv.2012.15477","title":"Particle Dual Averaging: Optimization of Mean Field Neural Networks with Global Convergence Rate Analysis","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Convergence (economics); Artificial neural network; Rate of convergence; Mathematical optimization; Nonlinear system; Computer science; Empirical risk minimization; Inner loop; Applied mathematics; Mathematics; Artificial intelligence; Physics; Key (lock)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001962143,0.000825966,0.001090013,0.0005394619,0.0003793835,0.001028866,0.001254414,0.001203238,0.001266969],"category_scores_gemma":[0.005844381,0.0005403179,0.0005748483,0.0005083539,0.001270334,0.001547516,0.001806991,0.001460199,0.0002682502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008676288,"about_ca_system_score_gemma":0.001081588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001812246,"about_ca_topic_score_gemma":0.001240763,"domain_scores_codex":[0.9994668,0.0002231768,0.00002018265,0.00009092717,0.0001517632,0.00004714932],"domain_scores_gemma":[0.9986573,0.0007788814,0.0001427802,0.0001171092,0.0002238677,0.00008012911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004899696,0.00002895205,0.0003925932,0.00006376948,0.0000497799,0.00004459191,0.000037821,0.8865,0.002031967,0.08497828,0.001239707,0.02458356],"study_design_scores_gemma":[0.000001802285,0.000004477691,0.0000130043,0.000001188781,0.000001144113,0.000002583173,6.579824e-7,0.9930428,0.0001377984,0.00668677,0.0001062861,0.00000152587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006799068,0.0001315924,0.9916768,0.0001708001,0.00003565683,0.00001180421,0.0000144747,0.0001033055,0.001056542],"genre_scores_gemma":[0.5798909,0.000461673,0.412381,0.0003043755,0.0002222785,0.0002394438,0.000141283,0.0003579839,0.006001106],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001962143,"threshold_uncertainty_score":0.01037693,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04547622419307678,"score_gpt":0.1913538874143895,"score_spread":0.1458776632213127,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}